© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 17771
    Prev
    Next
    INDEX
    Explanations

    references to judges and the judicial system

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MonoBehaviour
    -0.75
     BoxFit
    -0.69
    ReusableCell
    -0.62
     незавершена
    -0.62
    EDEFAULT
    -0.62
    apimachinery
    -0.60
    ❉
    -0.59
     فريبيس
    -0.59
     OFDb
    -0.59
    ]-'
    -0.59
    POSITIVE LOGITS
     Judiciary
    0.84
     judicial
    0.75
    Judicial
    0.74
     Judicial
    0.72
     juris
    0.69
     Juris
    0.69
     judiciary
    0.66
    judicial
    0.64
    Juris
    0.64
     JUDICIAL
    0.64
    Activations Density 0.158%

    No Known Activations